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. 53240
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
     база
    -0.08
     öpp
    -0.08
    高さ
    -0.08
     wagering
    -0.08
     recursion
    -0.08
     hatua
    -0.07
    xffffffff
    -0.07
     awood
    -0.07
    �
    -0.07
     handy
    -0.07
    POSITIVE LOGITS
     descriptor
    0.08
     islands
    0.08
     copro
    0.08
    Descriptor
    0.07
    ×↵↵
    0.07
     Descriptor
    0.07
    (${
    0.07
    (store
    0.07
     parliamentary
    0.07
    Meaning
    0.07
    Activations Density 0.008%

    No Known Activations