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. 15-RESID-POST-AA
    6. 19004
    Prev
    Next
    INDEX
    Explanations

    .train or .eval

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الذهب
    -0.07
    _song
    -0.07
    ..."
    -0.07
    ?"
    -0.07
    ":
    -0.07
     song
    -0.07
    ेली
    -0.07
    imento
    -0.07
     игре
    -0.06
    95
    -0.06
    POSITIVE LOGITS
    awm
    0.08
     ggf
    0.08
     trạng
    0.08
    .Ap
    0.07
    //----------------------------------------------------------------
    0.07
     semantics
    0.07
     ↓
    0.07
     ذر
    0.07
     वात
    0.07
    ômage
    0.07
    Activations Density 0.000%

    No Known Activations