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. 77444
    Prev
    Next
    INDEX
    Explanations

    args

    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
     త
    -0.10
    rose
    -0.08
     Johnny
    -0.08
     వై
    -0.08
     tits
    -0.07
    帖
    -0.07
     lichaam
    -0.07
    xffff
    -0.07
    upload
    -0.07
     negro
    -0.07
    POSITIVE LOGITS
    =json
    0.08
    "text
    0.08
    	json
    0.08
    "name
    0.08
    $json
    0.08
    _JSON
    0.08
    iane
    0.07
     edema
    0.07
    =""
    0.07
     expressed
    0.07
    Activations Density 0.001%

    No Known Activations