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. 59709
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
     constantemente
    -0.08
     mensch
    -0.08
     constantly
    -0.07
    antwoord
    -0.07
    움을
    -0.07
    मह
    -0.07
    Он
    -0.07
    пол
    -0.07
    豪
    -0.07
    ونه
    -0.07
    POSITIVE LOGITS
     размещ
    0.08
    ORS
    0.08
    ających
    0.08
     fonction
    0.08
     والے
    0.08
     функций
    0.08
    _INTERNAL
    0.07
    ajaj
    0.07
     اما
    0.07
     boc
    0.07
    Activations Density 0.000%

    No Known Activations