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. 98103
    Prev
    Next
    INDEX
    Explanations

    Not

    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
     cał
    -0.10
     क्योंकि
    -0.09
     gehele
    -0.09
     complications
    -0.08
    ,因为
    -0.08
     alterations
    -0.08
     aangezien
    -0.08
    ేశారు
    -0.08
     degenen
    -0.08
     бүх
    -0.08
    POSITIVE LOGITS
     familiar
    0.17
     aware
    0.15
     ringing
    0.14
     common
    0.14
     mainstream
    0.14
     bekannte
    0.13
    熟
    0.13
     prominent
    0.12
     widespread
    0.12
    common
    0.12
    Activations Density 0.016%

    No Known Activations