© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49981
    Prev
    Next
    INDEX
    Explanations

    equal sign

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .backward
    -0.09
    caling
    -0.09
    <>();
↵
    -0.08
    -backed
    -0.08
    .roll
    -0.08
     fleste
    -0.07
    ubal
    -0.07
     vanzelf
    -0.07
    يش
    -0.07
     rostro
    -0.07
    POSITIVE LOGITS
    _k
    0.10
     k
    0.10
     ...,
    0.09
     ...
    0.09
     Ар
    0.09
     Ar
    0.09
     n
    0.09
     {...
    0.09
     ....
    0.09
     positions
    0.09
    Activations Density 0.029%

    No Known Activations