© 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. 31039
    Prev
    Next
    INDEX
    Explanations

    Numbers and quantities

    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
    чив
    -0.07
     sein
    -0.07
     continuity
    -0.07
    луш
    -0.07
    .tools
    -0.07
    hani
    -0.07
     কিন
    -0.07
    olutions
    -0.06
    ’an
    -0.06
     therapeut
    -0.06
    POSITIVE LOGITS
     fewer
    0.09
     എണ്ണം
    0.09
     neçə
    0.09
     wenigen
    0.08
     shrug
    0.08
     sahaja
    0.08
    以内
    0.08
     NIV
    0.08
     kuv
    0.08
    တော့
    0.08
    Activations Density 0.081%

    No Known Activations