© 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. 12866
    Prev
    Next
    INDEX
    Explanations

    that

    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
    azor
    -0.10
    varen
    -0.09
    হার
    -0.09
     বেশ
    -0.08
     кадров
    -0.08
     reta
    -0.08
    adara
    -0.08
    fonos
    -0.07
    fed
    -0.07
     많
    -0.07
    POSITIVE LOGITS
     famous
    0.08
     fancy
    0.08
     mir
    0.07
     Ritual
    0.07
    ijski
    0.07
     controvers
    0.07
    ીઓ
    0.07
     Gi
    0.07
     ritual
    0.07
     STORY
    0.07
    Activations Density 0.000%

    No Known Activations