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. 11633
    Prev
    Next
    INDEX
    Explanations

    ?

    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
     leuc
    -0.09
     izvo
    -0.08
     бок
    -0.08
     lide
    -0.08
     rhe
    -0.07
     із
    -0.07
     Gareth
    -0.07
     निष
    -0.07
    phrase
    -0.07
    jquery
    -0.07
    POSITIVE LOGITS
     Geno
    0.08
     tales
    0.08
     desperate
    0.08
     المرض
    0.08
    给予
    0.08
    \x
    0.08
    _OF
    0.08
     persecution
    0.08
    急
    0.08
     bothering
    0.07
    Activations Density 0.023%

    No Known Activations