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. 9263
    Prev
    Next
    INDEX
    Explanations

    ation

    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
     rå
    -0.08
    ौं
    -0.07
    -0.07
     accompanying
    -0.07
     Belg
    -0.07
     لو
    -0.07
     blind
    -0.07
     hind
    -0.07
    .Buffer
    -0.07
    ഗ്ര
    -0.07
    POSITIVE LOGITS
    病例
    0.09
     deciding
    0.08
    ানে
    0.08
     Orientierung
    0.08
     drinking
    0.08
    ారణ
    0.08
    uctions
    0.08
     зв
    0.08
    idin
    0.08
     apoptosis
    0.08
    Activations Density 0.002%

    No Known Activations