© 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. 31056
    Prev
    Next
    INDEX
    Explanations

    alignment

    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
    應
    -0.09
    托
    -0.08
    ע
    -0.08
     Ai
    -0.08
    Captcha
    -0.08
     moderate
    -0.08
     liters
    -0.08
    代表
    -0.08
     aerobic
    -0.07
     pneumatic
    -0.07
    POSITIVE LOGITS
    alignment
    0.10
    Alignment
    0.10
     alignment
    0.10
     alinh
    0.09
     Align
    0.09
     Alignment
    0.09
    Align
    0.09
    -align
    0.09
    aligned
    0.08
     સ્થિતિ
    0.08
    Activations Density 0.007%

    No Known Activations