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. 58461
    Prev
    Next
    INDEX
    Explanations

    .commit

    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
     bouncing
    -0.09
     Bally
    -0.08
    _lb
    -0.08
    ariam
    -0.08
    登陆
    -0.08
    .attrib
    -0.08
    уз
    -0.08
     Battery
    -0.08
    NZ
    -0.07
    atè
    -0.07
    POSITIVE LOGITS
     investigative
    0.09
     investigators
    0.08
     krav
    0.07
     tet
    0.07
     päiv
    0.07
     修改
    0.07
    icorp
    0.07
     ids
    0.07
    正文
    0.07
     až
    0.07
    Activations Density 0.001%

    No Known Activations