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. 112168
    Prev
    Next
    INDEX
    Explanations

    hon

    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
    ോഹ
    -0.08
    _setopt
    -0.08
    メリ
    -0.08
    oral
    -0.08
    _letters
    -0.08
    pel
    -0.07
     Atlanta
    -0.07
     bati
    -0.07
    _fold
    -0.07
    çil
    -0.07
    POSITIVE LOGITS
     देती
    0.08
     durant
    0.08
     നൽകി
    0.07
     Herman
    0.07
     kemungkinan
    0.07
     Ner
    0.07
     Martín
    0.07
    aniya
    0.07
     wizard
    0.07
    /Re
    0.07
    Activations Density 0.000%

    No Known Activations