© 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. 19-RESID-POST-AA
    11. 21858
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     commanders
    -0.08
     unavoidable
    -0.08
     décl
    -0.08
     covert
    -0.08
    벤트
    -0.08
     compulsory
    -0.07
    fortawesome
    -0.07
    Activated
    -0.07
     traurig
    -0.07
     mandatory
    -0.07
    POSITIVE LOGITS
    _guess
    0.20
     iterations
    0.18
     guess
    0.18
     iteration
    0.18
    Iteration
    0.18
    Iterations
    0.18
     guesses
    0.18
     Guess
    0.17
    guess
    0.17
    _iterations
    0.17
    Activations Density 0.009%

    No Known Activations