© 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. 6200
    Prev
    Next
    INDEX
    Explanations

    registry

    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
    .Round
    -0.08
     conferencing
    -0.08
    ilat
    -0.08
    culpt
    -0.08
    arrow
    -0.07
    Arrow
    -0.07
     troubleshooting
    -0.07
    _percent
    -0.07
    #aa
    -0.07
    .Skip
    -0.07
    POSITIVE LOGITS
    ทะเบียน
    0.20
     Registry
    0.20
     രജ
    0.20
     registry
    0.20
    登记
    0.20
     registros
    0.19
     Registro
    0.19
     registr
    0.19
    Registry
    0.19
     registers
    0.19
    Activations Density 0.034%

    No Known Activations