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. 102753
    Prev
    Next
    INDEX
    Explanations

    rest

    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
    /Re
    -0.09
     Intermediate
    -0.08
    beschreibung
    -0.08
    atures
    -0.08
    詞
    -0.08
    ვე�
    -0.08
    Intermediate
    -0.08
    _stdio
    -0.07
    чы
    -0.07
    बार
    -0.07
    POSITIVE LOGITS
     أنحاء
    0.09
    0.08
    imas
    0.07
     recyclable
    0.07
    YES
    0.07
    Parts
    0.07
     parts
    0.07
    -the
    0.07
     हिस्स
    0.07
     lava
    0.07
    Activations Density 0.012%

    No Known Activations