© 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. 26409
    Prev
    Next
    INDEX
    Explanations

    Start of sentences

    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
     tiap
    -0.10
     составе
    -0.10
     écht
    -0.09
     réellement
    -0.09
     tadi
    -0.08
     любых
    -0.08
     irgendwel
    -0.08
     egentligen
    -0.08
     IVA
    -0.08
     purposely
    -0.08
    POSITIVE LOGITS
    <|endoftext|>
    0.16
     apologize
    0.09
    Title
    0.09
     Your
    0.09
     있습니다
    0.09
    Translation
    0.09
    以下
    0.08
    您的
    0.08
    Here's
    0.08
    Lo
    0.08
    Activations Density 0.637%

    No Known Activations