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. 120014
    Prev
    Next
    INDEX
    Explanations

    game

    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
     مار
    -0.08
     grasp
    -0.08
    _ERR
    -0.08
     marketer
    -0.08
    شان
    -0.08
     secundaria
    -0.08
    ಿಂಗ್
    -0.08
     fire
    -0.08
    _MAIL
    -0.07
    研
    -0.07
    POSITIVE LOGITS
    双方
    0.10
     disputa
    0.10
     ঘটে
    0.09
     xảy
    0.09
     జరుగ
    0.09
     adjud
    0.09
     జరిగ
    0.08
     Comit
    0.08
     dérou
    0.08
     decorrer
    0.08
    Activations Density 0.011%

    No Known Activations