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. 112111
    Prev
    Next
    INDEX
    Explanations

    assumed

    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
     शांत
    -0.08
     Une
    -0.08
     lesquelles
    -0.08
     waarom
    -0.07
     Path
    -0.07
     varför
    -0.07
     Certaines
    -0.07
     AL
    -0.07
    ATALOG
    -0.07
     Books
    -0.07
    POSITIVE LOGITS
    ائس
    0.09
    怀
    0.08
     zi
    0.08
    iziert
    0.08
    άνι
    0.08
    widget
    0.08
    stitute
    0.08
    :z
    0.08
    besondere
    0.08
    �
    0.08
    Activations Density 0.000%

    No Known Activations