© 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. 94911
    Prev
    Next
    INDEX
    Explanations

    or

    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
    ryk
    -0.08
    ṣẹ
    -0.08
     Fog
    -0.07
     jó
    -0.07
    ividades
    -0.07
     por
    -0.07
    tempt
    -0.07
    /T
    -0.07
     fog
    -0.07
     gong
    -0.07
    POSITIVE LOGITS
     yayi
    0.09
     depending
    0.08
     नहीं
    0.08
    ுள்ளது
    0.08
     નહીં
    0.08
     નહિ
    0.08
     yiri
    0.08
     नही
    0.08
    fi
    0.08
    ably
    0.08
    Activations Density 0.021%

    No Known Activations