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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 97985
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fourth
    -0.11
     Third
    -0.11
     fourth
    -0.11
     ಠಾಣ
    -0.10
     attave
    -0.10
     الثلاث
    -0.10
     quatrième
    -0.10
     aamma
    -0.10
     ilaat
    -0.10
     naalakkersuis
    -0.10
    POSITIVE LOGITS
    �
    0.08
    isch
    0.07
    mathbf
    0.06
    ök
    0.06
    (timeout
    0.06
    ieß
    0.06
    ische
    0.06
    ocker
    0.06
     discount
    0.06
    lags
    0.06
    Activations Density 0.462%

    No Known Activations