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. 43155
    Prev
    Next
    INDEX
    Explanations

    иль

    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
    _style
    -0.08
    classic
    -0.08
    ifra
    -0.07
     यात
    -0.07
    иком
    -0.07
    իկ
    -0.07
    pai
    -0.07
     heights
    -0.07
    最佳
    -0.07
     Optimal
    -0.07
    POSITIVE LOGITS
     जोर
    0.10
     силь
    0.08
    -strength
    0.08
    _strength
    0.08
     vend
    0.08
     lockdown
    0.08
     fuertes
    0.07
     dent
    0.07
     sar
    0.07
    弱
    0.07
    Activations Density 0.011%

    No Known Activations