Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43804
    Prev
    Next
    INDEX
    Explanations

    234

    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
     Axios
    -0.09
     sal
    -0.08
     punya
    -0.07
    urtles
    -0.07
    amut
    -0.07
     الرج
    -0.07
     ό
    -0.07
     environmental
    -0.07
     pytest
    -0.07
     συμβ
    -0.07
    POSITIVE LOGITS
    VH
    0.09
     Villar
    0.08
    mm
    0.08
     vele
    0.08
    bb
    0.07
    _ff
    0.07
    VG
    0.07
     ggf
    0.07
    òd
    0.07
    itel
    0.07
    Activations Density 3.321%

    No Known Activations