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. 109397
    Prev
    Next
    INDEX
    Explanations

    |

    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
    ೕ
    -0.09
     Ил
    -0.08
     unre
    -0.08
    _geom
    -0.08
     greek
    -0.08
     andet
    -0.08
    珠
    -0.08
     whichever
    -0.08
     travaillent
    -0.08
     Martha
    -0.07
    POSITIVE LOGITS
     aconse
    0.07
     Consejo
    0.07
    0.07
    (Action
    0.07
     chắn
    0.07
     mérito
    0.07
     carpeta
    0.07
    TP
    0.07
     Core
    0.07
    Tree
    0.07
    Activations Density 0.015%

    No Known Activations