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. 8980
    Prev
    Next
    INDEX
    Explanations

    ratatouille

    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
     அப
    -0.08
     sleep
    -0.08
    (login
    -0.08
     protr
    -0.08
     diameter
    -0.07
    (Login
    -0.07
     James
    -0.07
     зов
    -0.07
    (len
    -0.07
     ascent
    -0.07
    POSITIVE LOGITS
     bam
    0.08
     mezcl
    0.08
     mixt
    0.08
     batalla
    0.08
    ичный
    0.08
     basket
    0.08
    农村
    0.07
    杂
    0.07
    ブル
    0.07
    ্তু
    0.07
    Activations Density 0.003%

    No Known Activations