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. 119294
    Prev
    Next
    INDEX
    Explanations

    asterisk

    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
    ové
    -0.08
    ists
    -0.07
    ಿಶ
    -0.07
     cree
    -0.07
     vot
    -0.07
    Integrator
    -0.07
    <p
    -0.07
     dentists
    -0.06
     donkey
    -0.06
    附近
    -0.06
    POSITIVE LOGITS
    226
    0.08
     Basel
    0.08
     bolig
    0.08
    idle
    0.08
     voordat
    0.08
     соль
    0.08
    غاية
    0.08
    суз
    0.07
    (Bytes
    0.07
     bijdrage
    0.07
    Activations Density 0.016%

    No Known Activations