Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12609
    Prev
    Next
    INDEX
    Explanations

    MATLAB code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    304
    -0.08
    965
    -0.08
    ocar
    -0.08
    04
    -0.07
    .print
    -0.07
     ed
    -0.07
     Greater
    -0.07
    961
    -0.07
    CE
    -0.07
    925
    -0.07
    POSITIVE LOGITS
     ആവ
    0.09
     iterate
    0.08
    .Helper
    0.08
     esquina
    0.07
     Jeans
    0.07
    ছ
    0.07
    .grp
    0.07
     ഇട
    0.07
    voie
    0.07
     perman
    0.07
    Activations Density 0.000%

    No Known Activations