© 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. 23-RESID-POST-AA
    6. 48197
    Prev
    Next
    INDEX
    Explanations

    thi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entirely
    -0.08
     substit
    -0.08
    pairs
    -0.08
     replaces
    -0.08
     replacing
    -0.08
     remplacer
    -0.08
     opponents
    -0.08
    shift
    -0.08
    uidor
    -0.07
    uaje
    -0.07
    POSITIVE LOGITS
    ết
    0.10
    inking
    0.09
    erry
    0.09
     đấu
    0.08
    ếu
    0.08
    ệu
    0.08
    ssen
    0.08
    ằng
    0.07
     Flu
    0.07
     Indexed
    0.07
    Activations Density 0.002%

    No Known Activations