© 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. 71196
    Prev
    Next
    INDEX
    Explanations

    description

    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
     Robust
    -0.08
     Surveillance
    -0.08
     examined
    -0.08
     ISR
    -0.08
     David
    -0.07
     Nature
    -0.07
     Surveys
    -0.07
     robust
    -0.07
    eer
    -0.07
     Somm
    -0.07
    POSITIVE LOGITS
     lleva
    0.09
    (label
    0.08
    ylabel
    0.08
     verbs
    0.08
     없이
    0.08
     ylabel
    0.08
     nouns
    0.08
    (Label
    0.08
     puntu
    0.08
     Bento
    0.08
    Activations Density 0.002%

    No Known Activations