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. 48982
    Prev
    Next
    INDEX
    Explanations

    base

    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
     entrant
    -0.08
    -speaking
    -0.08
    択
    -0.08
     insider
    -0.07
    157
    -0.07
     synonyms
    -0.07
     renseign
    -0.07
     القادمة
    -0.07
    -send
    -0.07
    武
    -0.07
    POSITIVE LOGITS
     마련
    0.10
     sturdy
    0.10
    底
    0.09
     beneath
    0.09
     grounding
    0.09
     stevig
    0.09
    idee
    0.08
    eux
    0.08
    skirts
    0.08
    裙
    0.08
    Activations Density 0.014%

    No Known Activations