Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19311
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pdata
    -0.09
    hots
    -0.08
    siwaju
    -0.08
    (valid
    -0.08
     Diret
    -0.07
    бин
    -0.07
    RP
    -0.07
     beper
    -0.07
     RP
    -0.07
    Validated
    -0.07
    POSITIVE LOGITS
     seit
    0.08
     systems
    0.08
     Augen
    0.07
     
    0.07
     Leonard
    0.07
     વાગ
    0.07
     nerves
    0.07
     constructing
    0.07
    strijd
    0.07
     certaine
    0.07
    Activations Density 0.028%

    No Known Activations