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. 58419
    Prev
    Next
    INDEX
    Explanations

    thousands

    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
     bekannten
    -0.09
     bekannte
    -0.09
     Fitness
    -0.08
     Yoga
    -0.08
     Known
    -0.08
     извест
    -0.07
     yoga
    -0.07
    �
    -0.07
     inducing
    -0.07
    olly
    -0.07
    POSITIVE LOGITS
     flank
    0.08
     ocult
    0.08
     desist
    0.08
    -largest
    0.08
     vowel
    0.08
    digit
    0.08
    most
    0.08
     자리
    0.08
     عشر
    0.08
    Reserved
    0.07
    Activations Density 0.015%

    No Known Activations