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. 58535
    Prev
    Next
    INDEX
    Explanations

    Unverified/unprocessed claims or waste

    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
     Charles
    -0.09
    iveau
    -0.08
    sun
    -0.08
     Ст
    -0.08
     എല്ല
    -0.08
    Charles
    -0.07
    entiel
    -0.07
    že
    -0.07
    اني
    -0.07
     cały
    -0.07
    POSITIVE LOGITS
    -standing
    0.08
     unor
    0.08
     निर्�
    0.08
    않
    0.08
     Kosovo
    0.07
     않은
    0.07
     türlü
    0.07
     विदेशी
    0.07
     않습니다
    0.07
    imately
    0.07
    Activations Density 0.039%

    No Known Activations