© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108712
    Prev
    Next
    INDEX
    Explanations

    assistant

    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
     CRC
    -0.07
    ority
    -0.07
     cob
    -0.07
     TLC
    -0.07
     apar
    -0.07
     Components
    -0.07
     Griff
    -0.07
    ‌ترین
    -0.07
     comun
    -0.07
    eners
    -0.07
    POSITIVE LOGITS
    <|channel|>
    0.09
     replied
    0.09
     silence
    0.09
    _reply
    0.09
     replying
    0.08
    Replies
    0.08
     responses
    0.08
     Silence
    0.08
     replies
    0.08
     hingegen
    0.08
    Activations Density 0.113%

    No Known Activations