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. 45006
    Prev
    Next
    INDEX
    Explanations

    elastic

    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
    iet
    -0.08
     velen
    -0.08
    -wow
    -0.08
     माथ
    -0.07
    גד
    -0.07
    요
    -0.07
     negativity
    -0.07
     FLOW
    -0.07
     onboard
    -0.07
    auth
    -0.07
    POSITIVE LOGITS
     intercambio
    0.08
     preserves
    0.08
     Uch
    0.08
     сохраня
    0.08
     preservar
    0.08
     NPC
    0.08
     mantiene
    0.08
     MDC
    0.08
     conserva
    0.07
    瓜
    0.07
    Activations Density 0.001%

    No Known Activations