© 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. 5795
    Prev
    Next
    INDEX
    Explanations

    混

    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
    ীক্ষ
    -0.08
    _PATCH
    -0.08
    ικ
    -0.08
     patch
    -0.08
    ിക്ഷ
    -0.08
     tomou
    -0.08
    әге
    -0.08
    (enc
    -0.08
    يك
    -0.08
     MICRO
    -0.08
    POSITIVE LOGITS
    territ
    0.08
    bool
    0.08
    embrance
    0.07
    []}
    0.07
    	bool
    0.07
    cw
    0.07
    }-{
    0.07
    同行
    0.07
    aland
    0.07
     outras
    0.07
    Activations Density 0.001%

    No Known Activations