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. 78541
    Prev
    Next
    INDEX
    Explanations

    player

    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
     defens
    -0.08
     Guerrero
    -0.08
    .orm
    -0.08
    lar
    -0.07
    ક્રમ
    -0.07
    Sequence
    -0.07
     contraire
    -0.07
    .dev
    -0.07
    ক্রম
    -0.07
    ratings
    -0.07
    POSITIVE LOGITS
     tara
    0.09
    aque
    0.09
     عق
    0.08
     multip
    0.08
     agu
    0.08
     equipments
    0.08
     baja
    0.08
    aska
    0.08
     Avalon
    0.08
     avid
    0.08
    Activations Density 0.004%

    No Known Activations