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. 67206
    Prev
    Next
    INDEX
    Explanations

    philosophy

    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
     Knit
    -0.08
     subsidy
    -0.08
    剪
    -0.08
     RN
    -0.08
    dır
    -0.08
    PAT
    -0.08
     knitted
    -0.08
    bies
    -0.07
     sinus
    -0.07
    액
    -0.07
    POSITIVE LOGITS
    理念
    0.11
     ihr
    0.09
     outlook
    0.09
    观点
    0.09
     philos
    0.08
    哲
    0.08
    osu
    0.08
     wellness
    0.08
    藏
    0.07
     underpin
    0.07
    Activations Density 0.009%

    No Known Activations