© 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. 48127
    Prev
    Next
    INDEX
    Explanations

    方

    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
    SUR
    -0.08
    sono
    -0.08
    _std
    -0.07
    urface
    -0.07
    hle
    -0.07
    WHO
    -0.07
    jx
    -0.07
     тор
    -0.07
    uree
    -0.07
    ்கள்
    -0.07
    POSITIVE LOGITS
    程
    0.15
    块
    0.13
    位
    0.12
    舟
    0.11
    言
    0.11
    差
    0.09
    针
    0.09
    寸
    0.09
    括
    0.09
    �
    0.08
    Activations Density 0.006%

    No Known Activations