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. 112297
    Prev
    Next
    INDEX
    Explanations

    I

    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
    陌
    -0.08
    (Channel
    -0.08
    >(↵
    -0.08
     Channel
    -0.07
     meanings
    -0.07
    ര
    -0.07
    >".
    -0.07
    okk
    -0.07
    >Total
    -0.07
     смыс
    -0.07
    POSITIVE LOGITS
    入住
    0.09
     располага
    0.08
     halfway
    0.08
     Gerald
    0.08
     travels
    0.08
     astore
    0.08
     čin
    0.08
     صلى
    0.08
     रहते
    0.08
     πάνω
    0.08
    Activations Density 0.031%

    No Known Activations