© 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. 69984
    Prev
    Next
    INDEX
    Explanations

    :

    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
     అనే
    -0.08
    NER
    -0.08
     তখন
    -0.07
    Git
    -0.07
     publiques
    -0.07
     여부
    -0.07
     എന്ന്
    -0.07
    _visibility
    -0.07
    aw
    -0.07
    enet
    -0.07
    POSITIVE LOGITS
    route
    0.09
     blom
    0.08
     flour
    0.08
     autour
    0.08
    ški
    0.08
     amet
    0.08
     oktober
    0.08
     कल
    0.08
     alrededor
    0.08
     Ans
    0.08
    Activations Density 0.052%

    No Known Activations