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. 12043
    Prev
    Next
    INDEX
    Explanations

    face

    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
    假的
    -0.08
     паб
    -0.08
     MU
    -0.08
    ाँ
    -0.08
     विधान
    -0.07
     cav
    -0.07
     Heng
    -0.07
     tulem
    -0.07
     governor
    -0.07
     bekannte
    -0.07
    POSITIVE LOGITS
    �
    0.09
     Arabic
    0.09
     ಪ್ರದೇಶ
    0.08
    _AREA
    0.08
     دائ
    0.08
     વિસ્તાર
    0.08
     영역
    0.08
     područ
    0.08
     almonds
    0.08
    Arabic
    0.08
    Activations Density 0.047%

    No Known Activations