© 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. 78860
    Prev
    Next
    INDEX
    Explanations

    Directional movement patterns

    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
    _labels
    -0.07
    _DECLARE
    -0.07
    Labels
    -0.07
     Germ
    -0.07
     miche
    -0.07
     resemblance
    -0.07
    /lic
    -0.07
     throwing
    -0.07
     Represents
    -0.07
    hep
    -0.07
    POSITIVE LOGITS
    长沙
    0.09
    一路
    0.09
     vervolgens
    0.08
     anschließend
    0.08
    沿
    0.08
    .-
    0.08
     لمدة
    0.08
     ‍
    0.08
    順
    0.08
    完
    0.07
    Activations Density 0.013%

    No Known Activations