© 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. 75542
    Prev
    Next
    INDEX
    Explanations

    Conversational/dialogue text

    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
     Particularly
    -0.08
     Chall
    -0.08
    ाँच
    -0.08
     Assess
    -0.08
     bombing
    -0.07
    ப்பு
    -0.07
     Scores
    -0.07
     bana
    -0.07
     banna
    -0.07
     Refresh
    -0.07
    POSITIVE LOGITS
     durée
    0.08
    Duration
    0.08
     duration
    0.08
    Dur
    0.08
     dur
    0.08
     für
    0.07
     dla
    0.07
     এলাক
    0.07
     electromagnetic
    0.07
     utf
    0.07
    Activations Density 0.000%

    No Known Activations