© 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. 18297
    Prev
    Next
    INDEX
    Explanations

    is/are

    np_max-act-logits · gemini-2.0-flash
    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
     These
    -0.10
     seraient
    -0.09
     Others
    -0.09
     Are
    -0.09
     এসব
    -0.09
     മറ്റ്
    -0.09
     그리고
    -0.09
    );
    -0.09
    その他
    -0.09
     is
    -0.09
    POSITIVE LOGITS
     also
    0.14
     not
    0.14
     considered
    0.14
     an
    0.13
     a
    0.13
     used
    0.13
     called
    0.13
     the
    0.12
     always
    0.12
     going
    0.12
    Activations Density 0.502%

    No Known Activations