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. 60482
    Prev
    Next
    INDEX
    Explanations

    comparisons

    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
    -0.09
     high
    -0.08
    кового
    -0.07
    Equ
    -0.07
    High
    -0.07
     renta
    -0.07
    ഗ
    -0.06
     abar
    -0.06
    Equivalent
    -0.06
     SW
    -0.06
    POSITIVE LOGITS
     determinadas
    0.09
     blanc
    0.08
     тяж
    0.08
    .Priority
    0.08
     cybers
    0.08
     críticas
    0.08
     tumblr
    0.08
     amongst
    0.07
     spelers
    0.07
     Heidi
    0.07
    Activations Density 0.012%

    No Known Activations