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. 90256
    Prev
    Next
    INDEX
    Explanations

    sit

    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
     istil
    -0.07
     Pb
    -0.07
     phr
    -0.07
     Lem
    -0.07
    是多少
    -0.07
     Leakage
    -0.07
    hair
    -0.07
     tendency
    -0.07
    pbs
    -0.07
     hairstyle
    -0.07
    POSITIVE LOGITS
     poised
    0.10
    附近
    0.09
     hopeless
    0.08
     beneath
    0.08
    րա
    0.08
     passionately
    0.08
     hoped
    0.08
     innoc
    0.08
     soooo
    0.08
     openly
    0.08
    Activations Density 0.011%

    No Known Activations