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. 1581
    Prev
    Next
    INDEX
    Explanations

    Mass Effect (game)

    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
     dies
    -0.08
    .der
    -0.08
    割合
    -0.07
     marches
    -0.07
    голь
    -0.07
    .matches
    -0.07
    Gal
    -0.07
     spé
    -0.07
    直
    -0.07
    基地
    -0.07
    POSITIVE LOGITS
     corpo
    0.10
     BODY
    0.08
     Corpo
    0.08
     adc
    0.08
     cuerpo
    0.08
     ELECT
    0.07
     pretrained
    0.07
     Nai
    0.07
     CPA
    0.07
    eltje
    0.07
    Activations Density 0.000%

    No Known Activations