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. 3-RESID-POST-AA
    6. 1709
    Prev
    Next
    INDEX
    Explanations

    devanagari

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovir
    -0.08
    ovirus
    -0.08
     contradiction
    -0.08
     omnibus
    -0.08
     jac
    -0.08
     Shakespeare
    -0.08
     dilig
    -0.07
     Nui
    -0.07
    jene
    -0.07
    .orig
    -0.07
    POSITIVE LOGITS
     Rs
    0.08
     darb
    0.07
     लाग
    0.07
     chung
    0.07
     맞
    0.07
    কে
    0.07
    .collection
    0.07
     použ
    0.07
    nehmen
    0.07
     ap
    0.07
    Activations Density 0.001%

    No Known Activations