© 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. 48141
    Prev
    Next
    INDEX
    Explanations

    =

    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
     continuously
    -0.09
    continuous
    -0.09
    /news
    -0.09
     contín
    -0.09
    success
    -0.08
    const
    -0.08
     continuous
    -0.08
    /con
    -0.08
    never
    -0.08
     continues
    -0.08
    POSITIVE LOGITS
     జగ
    0.09
    ំហំ
    0.09
    робнее
    0.09
     zida
    0.09
    엇
    0.08
     gleiche
    0.08
     байланыш
    0.08
     თავს
    0.08
    ৰু
    0.08
    ্তারিত
    0.08
    Activations Density 0.014%

    No Known Activations