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. 98896
    Prev
    Next
    INDEX
    Explanations

    Non-English language

    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
     talentos
    -0.09
    Wood
    -0.08
     socioeconomic
    -0.08
    Talent
    -0.08
    leda
    -0.08
    .ec
    -0.08
    .bi
    -0.08
     వర
    -0.08
    .car
    -0.08
    势
    -0.07
    POSITIVE LOGITS
    िम्म
    0.09
     occasions
    0.08
     pudo
    0.08
    ugno
    0.08
     podido
    0.08
     встанов
    0.07
     остав
    0.07
    processable
    0.07
    ohu
    0.07
     установлен
    0.07
    Activations Density 0.056%

    No Known Activations