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. 156
    Prev
    Next
    INDEX
    Explanations

    natural cycles

    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
     predictors
    -0.09
     আপন
    -0.08
     axe
    -0.08
    Authorized
    -0.08
    using
    -0.08
    招
    -0.07
    achu
    -0.07
    boarding
    -0.07
    wv
    -0.07
    预约
    -0.07
    POSITIVE LOGITS
     terrestrial
    0.12
     sediment
    0.12
     Зем
    0.11
     sediments
    0.11
     зем
    0.11
     recycle
    0.10
     Recycling
    0.10
     Earth
    0.10
     पृथ
    0.10
     redistribute
    0.10
    Activations Density 0.010%

    No Known Activations