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. 49307
    Prev
    Next
    INDEX
    Explanations

    cancel

    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
    博
    -0.08
     interrog
    -0.07
    bath
    -0.07
    -0.07
     clara
    -0.07
     accords
    -0.07
     Jackson
    -0.07
     parte
    -0.07
     shum
    -0.07
     Ban
    -0.07
    POSITIVE LOGITS
    掉
    0.10
     outright
    0.09
     incurred
    0.09
    ABLE
    0.08
    撤
    0.08
     bỏ
    0.08
     связи
    0.08
    /In
    0.08
    isy
    0.08
    HV
    0.08
    Activations Density 0.006%

    No Known Activations