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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 54555
    Prev
    Next
    INDEX
    Explanations

    hints and subtle cues

    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
     ডিস
    -0.09
     ડિસ
    -0.08
    отор
    -0.08
     gripe
    -0.08
     foto
    -0.08
     Foto
    -0.08
     Noise
    -0.08
     шум
    -0.07
    _disp
    -0.07
     Verw
    -0.07
    POSITIVE LOGITS
     clues
    0.12
     ambiguous
    0.11
     messages
    0.11
    Messaging
    0.10
    Messages
    0.10
     संकेत
    0.10
     indiqu
    0.09
    messages
    0.09
     subtly
    0.09
     conveying
    0.09
    Activations Density 0.039%

    No Known Activations