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. 65077
    Prev
    Next
    INDEX
    Explanations

    erm

    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
     tutela
    -0.09
     karo
    -0.08
    ૧૯
    -0.08
     kanthi
    -0.07
     abstr
    -0.07
     tack
    -0.07
     Totally
    -0.07
    Dang
    -0.07
     recién
    -0.07
    Stan
    -0.07
    POSITIVE LOGITS
     carbonation
    0.09
     sexual
    0.08
     equ
    0.08
     menopause
    0.08
    ্যে
    0.07
    浴
    0.07
     sexually
    0.07
    筛
    0.07
     jabón
    0.07
     And
    0.07
    Activations Density 0.001%

    No Known Activations