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. 45118
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    Founder
    -0.09
     nat
    -0.07
    -0.07
     Founder
    -0.07
    착
    -0.07
     diminishing
    -0.07
     어
    -0.07
     decreasing
    -0.07
     很
    -0.07
     强
    -0.07
    POSITIVE LOGITS
    785
    0.08
    953
    0.08
     shaders
    0.08
    891
    0.08
     степ
    0.08
    892
    0.08
    _MP
    0.07
    810
    0.07
     Appreciation
    0.07
    894
    0.07
    Activations Density 0.128%

    No Known Activations