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. 90286
    Prev
    Next
    INDEX
    Explanations

    ход

    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
    ’d
    -0.08
    Brick
    -0.07
    brick
    -0.07
    ➡
    -0.07
     Brick
    -0.07
    霞
    -0.07
     bricks
    -0.07
     ticking
    -0.07
     eletr
    -0.07
    fc
    -0.07
    POSITIVE LOGITS
     siihen
    0.08
     thereto
    0.08
     pagb
    0.08
     sellele
    0.07
     إليها
    0.07
     seuls
    0.07
    ящие
    0.07
     जिससे
    0.07
    0.07
     لگا
    0.07
    Activations Density 0.009%

    No Known Activations