© 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. 23-RESID-POST-AA
    11. 5805
    Prev
    Next
    INDEX
    Explanations

    Mentions sisters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ||↵
    -0.07
    among
    -0.07
    _gr
    -0.07
     commerci
    -0.07
    odol
    -0.07
     grants
    -0.07
     ملا
    -0.07
     params
    -0.07
     mangg
    -0.07
    itsa
    -0.07
    POSITIVE LOGITS
    œurs
    0.09
    oe
    0.08
     Xe
    0.08
     Sabbath
    0.08
     jub
    0.08
     Logout
    0.08
     Orwell
    0.08
    황
    0.08
    _AUTO
    0.08
     Invis
    0.07
    Activations Density 0.000%

    No Known Activations