© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102669
    Prev
    Next
    INDEX
    Explanations

    Technical indicators

    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
     redact
    -0.10
     reimbursement
    -0.10
     plaza
    -0.09
     gowns
    -0.09
     gown
    -0.09
    廷
    -0.08
     runt
    -0.08
     Haag
    -0.08
    Billing
    -0.08
    .redirect
    -0.08
    POSITIVE LOGITS
     RSI
    0.16
     indikator
    0.16
     oscillator
    0.16
     مؤشر
    0.16
     indicador
    0.16
    指标
    0.15
     indicadores
    0.14
     bearish
    0.14
     indicator
    0.14
     indicators
    0.14
    Activations Density 0.009%

    No Known Activations