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. 9094
    Prev
    Next
    INDEX
    Explanations

    chiar

    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
    édi
    -0.08
    tect
    -0.08
    eren
    -0.07
     lia
    -0.07
    兼职
    -0.07
     Preconditions
    -0.07
    ivelmente
    -0.07
    ediation
    -0.07
     miễn
    -0.07
    aging
    -0.07
    POSITIVE LOGITS
     kontr
    0.09
     contraste
    0.09
     FIG
    0.09
    魂
    0.08
    contrast
    0.08
    opse
    0.08
     CONTR
    0.08
     contrast
    0.08
    Contrast
    0.08
    ない
    0.08
    Activations Density 0.000%

    No Known Activations