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. 111599
    Prev
    Next
    INDEX
    Explanations

    Suspenseful storytelling

    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
     exercices
    -0.08
     Expl
    -0.08
     অপর
    -0.07
     apolog
    -0.07
     poseen
    -0.07
     ----------------------------------------------------------------------------------------------------------------
    -0.07
    =("
    -0.07
    ехника
    -0.07
     IST
    -0.07
    న
    -0.07
    POSITIVE LOGITS
     trường
    0.08
     youngest
    0.08
     mada
    0.07
    enske
    0.07
     der
    0.07
    anni
    0.07
     tib
    0.07
     прямо
    0.07
    ANC
    0.07
     emocionante
    0.07
    Activations Density 0.003%

    No Known Activations