© 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. 108657
    Prev
    Next
    INDEX
    Explanations

    datasets

    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
     ошибки
    -0.09
     george
    -0.09
     الحرارة
    -0.08
     Guardians
    -0.08
     __(
    -0.08
    زا
    -0.08
     pamam
    -0.08
     galerie
    -0.08
     ошибок
    -0.08
    リング
    -0.08
    POSITIVE LOGITS
    NL
    0.09
     NL
    0.09
    Ba
    0.08
     indicted
    0.07
    Packet
    0.07
    199
    0.07
    Part
    0.07
    Ml
    0.07
     ftp
    0.07
    Dataset
    0.07
    Activations Density 0.005%

    No Known Activations