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. 43465
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Bhar
    -0.09
     thrust
    -0.09
    	th
    -0.08
     temel
    -0.08
     breasts
    -0.08
    intel
    -0.08
     insieme
    -0.08
     Bool
    -0.07
     दर्शन
    -0.07
    есть
    -0.07
    POSITIVE LOGITS
    $error
    0.08
     lowercase
    0.08
    arrera
    0.08
    ್ಲ
    0.08
    orgot
    0.08
     als
    0.08
     ocurrido
    0.07
     ALS
    0.07
     horario
    0.07
     туп
    0.07
    Activations Density 0.000%

    No Known Activations