© 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. 129564
    Prev
    Next
    INDEX
    Explanations

    Complex numbers and polynomials

    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
    _STATS
    -0.09
     Bewertungen
    -0.08
    评价
    -0.08
    减少
    -0.08
    突出
    -0.08
    downs
    -0.08
    JECTION
    -0.08
     στις
    -0.08
    评分
    -0.08
     vieles
    -0.08
    POSITIVE LOGITS
    state
    0.08
     decid
    0.07
    	state
    0.07
     mau
    0.07
    Set
    0.07
    angle
    0.07
     Oriental
    0.07
    Let's
    0.07
     Hewlett
    0.07
    ilic
    0.07
    Activations Density 0.013%

    No Known Activations