© 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. 23-RESID-POST-AA
    11. 48550
    Prev
    Next
    INDEX
    Explanations

    происх

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    schaft
    -0.08
     undesirable
    -0.07
    etermin
    -0.07
    ’il
    -0.07
     लोक
    -0.07
    aments
    -0.07
     unwanted
    -0.07
    undes
    -0.07
    fæ
    -0.07
    annoo
    -0.07
    POSITIVE LOGITS
    .number
    0.08
    .span
    0.08
     мол
    0.07
    Topo
    0.07
    Proto
    0.07
    .mouse
    0.07
     unfold
    0.07
    .mail
    0.07
    .ajax
    0.07
    .obtain
    0.07
    Activations Density 0.001%

    No Known Activations