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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 11850
    Prev
    Next
    INDEX
    Explanations

    carry over

    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
     inconvenient
    -0.08
    comod
    -0.08
     alfa
    -0.07
     frustr
    -0.07
     Igor
    -0.07
     فرو
    -0.07
     unpleasant
    -0.07
    strncmp
    -0.07
    ناک
    -0.07
     لندن
    -0.07
    POSITIVE LOGITS
    ่อ
    0.09
    Validators
    0.09
    Stake
    0.08
     Stake
    0.08
     bordering
    0.08
     stake
    0.08
    แม
    0.08
     mongoose
    0.08
     pristine
    0.07
     skyscr
    0.07
    Activations Density 0.001%

    No Known Activations