Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58941
    Prev
    Next
    INDEX
    Explanations

    not selling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Efficiency
    -0.08
    -0.07
     accomplished
    -0.07
     spells
    -0.07
    hee
    -0.07
     controls
    -0.07
     efficiency
    -0.07
    Spell
    -0.07
    Constraint
    -0.07
    _Init
    -0.07
    POSITIVE LOGITS
     monetize
    0.10
     yayın
    0.09
     terceros
    0.09
     verkaufen
    0.09
     nicht
    0.09
     데이터를
    0.09
    未经
    0.08
    UBLISH
    0.08
     개인정보
    0.08
     sells
    0.08
    Activations Density 0.018%

    No Known Activations