© 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. 23-RESID-POST-AA
    11. 49235
    Prev
    Next
    INDEX
    Explanations

    non-English

    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
     c
    -0.08
    _normal
    -0.07
    .protocol
    -0.07
    Normal
    -0.07
    રુ
    -0.07
     cartes
    -0.07
     cul
    -0.07
    .normal
    -0.07
     pioneers
    -0.07
     cef
    -0.07
    POSITIVE LOGITS
    ڈیا
    0.09
     passée
    0.09
    quinaria
    0.09
     vollkommen
    0.09
    kor
    0.09
    ifend
    0.09
    aksud
    0.09
    yenne
    0.09
    \Input
    0.09
    اسى
    0.08
    Activations Density 0.001%

    No Known Activations