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. 77177
    Prev
    Next
    INDEX
    Explanations

    between

    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
     വിവിധ
    -0.08
     steaming
    -0.08
     explores
    -0.07
     निय
    -0.07
     ഈ
    -0.07
     ห
    -0.07
     ପ
    -0.07
     regulates
    -0.07
     importantly
    -0.07
     oversees
    -0.07
    POSITIVE LOGITS
    مال
    0.09
     própria
    0.08
     megfelelő
    0.08
     Nec
    0.08
     propri
    0.08
     sara
    0.08
    مالك
    0.08
    ناسب
    0.08
    ریکی
    0.08
     factura
    0.07
    Activations Density 0.004%

    No Known Activations