© 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. 19-RESID-POST-AA
    11. 102736
    Prev
    Next
    INDEX
    Explanations

    scout

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     playlist
    -0.08
     degrad
    -0.08
     degradation
    -0.08
     curated
    -0.08
    _playlist
    -0.08
    playlist
    -0.08
    _end
    -0.08
     gist
    -0.08
     that
    -0.08
    /backend
    -0.08
    POSITIVE LOGITS
     Organizations
    0.14
     organizations
    0.14
    Organizations
    0.13
     Scouts
    0.13
    ®↵↵
    0.13
    ®.
    0.13
     organizaciones
    0.12
     Volunteer
    0.12
    organizations
    0.12
    ®
    0.11
    Activations Density 0.063%

    No Known Activations