© 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. 110645
    Prev
    Next
    INDEX
    Explanations

    period

    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
    polit
    -0.08
    ulho
    -0.08
    another
    -0.08
    Polit
    -0.08
     cancers
    -0.08
     Cui
    -0.08
     futuristic
    -0.08
    Indonesia
    -0.08
     ideias
    -0.08
     proactively
    -0.08
    POSITIVE LOGITS
     direkte
    0.08
     Same
    0.07
     >=
    0.07
     سور
    0.07
     widespread
    0.07
     '{}'
    0.07
     Attachment
    0.07
    .literal
    0.07
     Mand
    0.07
     Perl
    0.07
    Activations Density 0.008%

    No Known Activations