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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 18816
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sé
    -0.09
     both
    -0.08
    *n
    -0.08
     ―
    -0.08
     (>
    -0.08
    /be
    -0.08
     constitute
    -0.08
     �
    -0.07
    /stretch
    -0.07
    েতে
    -0.07
    POSITIVE LOGITS
     שמש
    0.08
    ITERAL
    0.08
     چې
    0.08
     שמת
    0.08
     avoids
    0.08
    	random
    0.08
     שיע
    0.07
     kiu
    0.07
     cuchar
    0.07
     દર
    0.07
    Activations Density 0.021%

    No Known Activations