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. 30004
    Prev
    Next
    INDEX
    Explanations

    total

    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
     gets
    -0.07
     padding
    -0.07
     voork
    -0.07
    гин
    -0.07
    �
    -0.07
    caster
    -0.07
    shape
    -0.07
    ல
    -0.07
    ki
    -0.07
     shaping
    -0.07
    POSITIVE LOGITS
     россий
    0.09
     Tym
    0.08
    econ
    0.08
     Ehren
    0.08
     mostram
    0.08
     વિન
    0.08
     Pharmacy
    0.08
     visita
    0.08
     القب
    0.08
     troca
    0.08
    Activations Density 0.003%

    No Known Activations