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. 76031
    Prev
    Next
    INDEX
    Explanations

    enter

    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
    ാട
    -0.08
     Champs
    -0.08
    .respond
    -0.08
     selectively
    -0.08
     Chic
    -0.07
    .delete
    -0.07
     selective
    -0.07
    Stacks
    -0.07
    ('$
    -0.07
     در
    -0.07
    POSITIVE LOGITS
     PLEASE
    0.09
     plum
    0.09
     descend
    0.08
     happier
    0.08
    YE
    0.08
    �
    0.08
     thong
    0.08
     DESC
    0.08
    "),
    0.08
     YE
    0.08
    Activations Density 0.000%

    No Known Activations