Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88193
    Prev
    Next
    INDEX
    Explanations

    another

    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
    اتے
    -0.08
    BU
    -0.08
    负责人
    -0.08
    NAM
    -0.08
    ки
    -0.08
     трев
    -0.08
    ત્રી
    -0.07
     فعالیت
    -0.07
     сем
    -0.07
    Representative
    -0.07
    POSITIVE LOGITS
     academically
    0.08
     obedient
    0.08
     apolog
    0.08
    ebe
    0.08
     Calder
    0.08
    无限
    0.07
     drywall
    0.07
    eddings
    0.07
    iewe
    0.07
     arbitr
    0.07
    Activations Density 0.000%

    No Known Activations