© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47119
    Prev
    Next
    INDEX
    Explanations

    Signal peptides/protein secretion

    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
    ším
    -0.08
    ších
    -0.08
     Chip
    -0.08
    坛
    -0.08
    采访
    -0.08
     bruke
    -0.08
    šit
    -0.08
    aż
    -0.07
    -0.07
     kig
    -0.07
    POSITIVE LOGITS
    /G
    0.08
    unciation
    0.08
     directing
    0.07
    :image
    0.07
     conductor
    0.07
    unci
    0.07
     voed
    0.07
    _ENTER
    0.07
    Sec
    0.07
    Suppress
    0.07
    Activations Density 0.001%

    No Known Activations