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. 43012
    Prev
    Next
    INDEX
    Explanations

    +

    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
     offline
    -0.07
    -memory
    -0.07
     archiv
    -0.07
     satisfied
    -0.07
     starving
    -0.07
     accepting
    -0.07
     Matching
    -0.07
    收到
    -0.07
    indow
    -0.07
    matching
    -0.07
    POSITIVE LOGITS
     quadratic
    0.10
     alteration
    0.09
     Acres
    0.08
     сочет
    0.08
    Alter
    0.08
     alterar
    0.08
     explos
    0.08
     tarik
    0.08
     alterations
    0.08
     alterações
    0.08
    Activations Density 0.047%

    No Known Activations