© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 70806
    Prev
    Next
    INDEX
    Explanations

    coding errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tickets
    -0.09
     pric
    -0.08
     subsid
    -0.08
     caller
    -0.08
     reimburse
    -0.08
     consomm
    -0.08
     boleto
    -0.07
     invoices
    -0.07
     распредел
    -0.07
     വിതരണം
    -0.07
    POSITIVE LOGITS
    _namespace
    0.10
     definitions
    0.09
    Declaration
    0.09
     이름
    0.09
     declarations
    0.09
    definitions
    0.09
    Namespace
    0.09
     namespace
    0.09
     선언
    0.09
    (namespace
    0.09
    Activations Density 0.008%

    No Known Activations