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. 120188
    Prev
    Next
    INDEX
    Explanations

    avoiding explicit content

    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
     활성
    -0.09
    .alg
    -0.08
     활용
    -0.08
    .Matcher
    -0.08
    ermanent
    -0.08
    ىلى
    -0.08
     জানা
    -0.07
     aktive
    -0.07
     Pedro
    -0.07
    ದುವ
    -0.07
    POSITIVE LOGITS
     tasteful
    0.13
     respectful
    0.12
     toned
    0.11
     innoc
    0.11
     eup
    0.11
     safer
    0.11
     moderate
    0.11
     respectable
    0.10
     subdued
    0.09
     turvall
    0.09
    Activations Density 0.030%

    No Known Activations