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. 7-RESID-POST-AA
    6. 1725
    Prev
    Next
    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     supply
    -0.08
    Св
    -0.08
     Supply
    -0.08
    _clk
    -0.08
    alk
    -0.08
    clk
    -0.08
    /root
    -0.08
    svg
    -0.07
    Roz
    -0.07
    passing
    -0.07
    POSITIVE LOGITS
    uphoria
    0.09
     Jenner
    0.09
     Lola
    0.08
     Indonesia
    0.08
    performance
    0.08
     Millennials
    0.08
    Efficiency
    0.08
     prophyl
    0.08
    중
    0.08
     효
    0.08
    Activations Density 0.040%

    No Known Activations