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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98579
    Prev
    Next
    INDEX
    Explanations

    other

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     these
    -0.12
     those
    -0.12
     a
    -0.10
     this
    -0.10
     the
    -0.09
     기타
    -0.09
     our
    -0.09
     your
    -0.09
     andre
    -0.09
     andra
    -0.09
    POSITIVE LOGITS
     than
    0.31
    -than
    0.30
    _than
    0.28
    Than
    0.26
    था
    0.25
    થા
    0.24
    than
    0.24
     THAN
    0.22
     Than
    0.22
     niż
    0.22
    Activations Density 0.138%

    No Known Activations