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. 112747
    Prev
    Next
    INDEX
    Explanations

    mixed language

    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
    ‌تواند
    -0.09
    ахь
    -0.09
    авис
    -0.08
    _black
    -0.08
    六合
    -0.08
    Blacklist
    -0.08
    िस
    -0.08
    ecs
    -0.08
     vérit
    -0.08
    უფ
    -0.08
    POSITIVE LOGITS
    闲
    0.07
     prvo
    0.07
     audio
    0.07
     entering
    0.07
     virgin
    0.07
     reserva
    0.07
     morb
    0.07
    JT
    0.07
    dbc
    0.07
     sonic
    0.07
    Activations Density 0.000%

    No Known Activations