Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 98455
    Prev
    Next
    INDEX
    Explanations

    quotation marks and "or"

    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
    Can
    -0.08
    Binary
    -0.07
     عوام
    -0.07
     emin
    -0.07
    Flatten
    -0.07
    Deposit
    -0.07
     weakness
    -0.07
    060
    -0.07
    Segment
    -0.07
     ',↵
    -0.07
    POSITIVE LOGITS
     praising
    0.08
     erabilt
    0.08
     Hitler
    0.07
     пользователей
    0.07
    ični
    0.07
    /AIDS
    0.07
     Encoding
    0.07
    ÑA
    0.07
     rant
    0.07
    -п
    0.07
    Activations Density 0.003%

    No Known Activations