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. 60522
    Prev
    Next
    INDEX
    Explanations

    of

    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
    .H
    -0.08
    .AR
    -0.08
     ર
    -0.08
     TIP
    -0.07
     ఏ
    -0.07
    PAR
    -0.07
    .Next
    -0.07
     HOT
    -0.07
     horseback
    -0.07
    KK
    -0.07
    POSITIVE LOGITS
     prepping
    0.09
     Sanit
    0.08
    ţ
    0.08
    判
    0.08
     judiciary
    0.08
     prä
    0.08
     (£
    0.08
    法院
    0.08
    ţe
    0.08
     আদাল
    0.07
    Activations Density 0.000%

    No Known Activations