Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 130996
    Prev
    Next
    INDEX
    Explanations

    break down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    援
    -0.10
    sf
    -0.08
     Puebla
    -0.08
     συνα
    -0.08
    三星
    -0.08
     shelving
    -0.08
    _sf
    -0.08
    _relationship
    -0.07
    abel
    -0.07
    ulich
    -0.07
    POSITIVE LOGITS
     infiltration
    0.08
    ्रीन
    0.08
     climb
    0.08
     carcin
    0.07
     paving
    0.07
     станов
    0.07
     सिक
    0.07
     �
    0.07
    Dive
    0.07
     Dive
    0.07
    Activations Density 0.001%

    No Known Activations