© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1306
    Prev
    Next
    INDEX
    Explanations

    geometric problem solving

    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
     humana
    -0.09
     pretrained
    -0.08
     Chemical
    -0.08
     Mathematical
    -0.08
     emot
    -0.08
     matur
    -0.08
    atta
    -0.08
     Overs
    -0.08
     humaine
    -0.08
    ecoin
    -0.07
    POSITIVE LOGITS
    117
    0.08
    Obt
    0.08
    Contact
    0.08
    116
    0.07
    Polygon
    0.07
     polygon
    0.07
     obt
    0.07
    =null
    0.07
    346
    0.07
     lunes
    0.07
    Activations Density 0.714%

    No Known Activations