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. 11-RESID-POST-AA
    6. 77158
    Prev
    Next
    INDEX
    Explanations

    x

    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
     مك
    -0.08
     lleno
    -0.08
    ्रीन
    -0.07
    ూల
    -0.07
     उद्घ
    -0.07
     Schal
    -0.07
    న్న
    -0.07
    辱
    -0.07
    tu
    -0.07
     Dol
    -0.07
    POSITIVE LOGITS
     correspondant
    0.09
    006
    0.09
    044
    0.08
    002
    0.08
     représ
    0.08
    -space
    0.08
     evaluates
    0.08
    001
    0.08
     Kashmir
    0.07
     correspond
    0.07
    Activations Density 0.024%

    No Known Activations