© 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. 103070
    Prev
    Next
    INDEX
    Explanations

    data

    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
     데이터
    -0.09
    켜
    -0.08
           
    -0.08
     hires
    -0.08
     ICT
    -0.08
     bidez
    -0.08
     kullan
    -0.08
     무료
    -0.08
     Datos
    -0.08
    _DATA
    -0.08
    POSITIVE LOGITS
     flows
    0.13
     flow
    0.13
    flow
    0.12
     movement
    0.12
     synchronization
    0.12
    -flow
    0.12
     movements
    0.11
    flows
    0.11
     model
    0.11
    _model
    0.11
    Activations Density 0.011%

    No Known Activations