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. 65069
    Prev
    Next
    INDEX
    Explanations

    5

    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
     bounce
    -0.10
     Bounce
    -0.08
    Lb
    -0.08
     tac
    -0.08
    テゴ
    -0.08
    bria
    -0.08
     empreendimento
    -0.08
     tuned
    -0.08
     LAB
    -0.07
     presumably
    -0.07
    POSITIVE LOGITS
     Denk
    0.08
     Normal
    0.08
     dão
    0.07
    Ple
    0.07
     Displays
    0.07
     waving
    0.07
    Há
    0.07
     Ple
    0.07
    Elektr
    0.07
     deram
    0.07
    Activations Density 0.003%

    No Known Activations