© 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. 7-RESID-POST-AA
    11. 1406
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     freien
    -0.08
    .free
    -0.08
     gauche
    -0.07
     gram
    -0.07
     freie
    -0.07
    自由
    -0.07
     trưởng
    -0.07
    free
    -0.07
     latin
    -0.07
     tans
    -0.07
    POSITIVE LOGITS
    ’om
    0.08
    ਵੇ
    0.08
     sistema
    0.08
     methodologies
    0.07
    ವೆ
    0.07
     principles
    0.07
    'om
    0.07
    டை
    0.07
     nodige
    0.07
    ancestor
    0.07
    Activations Density 0.007%

    No Known Activations