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. 52849
    Prev
    Next
    INDEX
    Explanations

    aman

    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
    Pile
    -0.08
     етеді
    -0.08
    uting
    -0.08
     CMOS
    -0.07
     полов
    -0.07
     pile
    -0.07
    idele
    -0.07
     ejército
    -0.07
     Blaze
    -0.07
     Mason
    -0.07
    POSITIVE LOGITS
    ಗಾರ
    0.08
    .Stop
    0.08
    .stop
    0.08
    ista
    0.08
    疗
    0.08
    ್ಗ
    0.08
     preached
    0.08
    Speak
    0.08
    术
    0.08
    Workshop
    0.07
    Activations Density 0.001%

    No Known Activations