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. 65411
    Prev
    Next
    INDEX
    Explanations

    transformations

    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
    hr
    -0.07
    (hr
    -0.07
     hr
    -0.07
    Quota
    -0.07
    -0.07
     Poor
    -0.07
    Pojo
    -0.07
    \Auth
    -0.07
     ಪ್ರಕರಣ
    -0.07
     a
    -0.07
    POSITIVE LOGITS
     permanecer
    0.09
    息
    0.09
     فوج
    0.08
     permanece
    0.08
    şg
    0.08
    naj
    0.08
    venido
    0.08
    签
    0.08
     Obwohl
    0.07
    款
    0.07
    Activations Density 0.001%

    No Known Activations