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. 78624
    Prev
    Next
    INDEX
    Explanations

    return

    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
    astern
    -0.08
    ameleon
    -0.07
     Esk
    -0.07
     apartado
    -0.07
     EM
    -0.07
     vivendo
    -0.07
     exponential
    -0.07
    printing
    -0.07
    breviation
    -0.07
    _EM
    -0.07
    POSITIVE LOGITS
    を
    0.09
     alleg
    0.08
    _CONFIRM
    0.08
     नए
    0.08
    arum
    0.08
    Nothing
    0.08
     Nothing
    0.08
     confirmação
    0.08
    通知
    0.08
     nothing
    0.08
    Activations Density 0.013%

    No Known Activations