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. 98217
    Prev
    Next
    INDEX
    Explanations

    180

    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
     Ing
    -0.11
     Om
    -0.11
    Om
    -0.11
    Ing
    -0.11
     Omni
    -0.09
     commissie
    -0.09
    Ol
    -0.09
     ilis
    -0.09
     om
    -0.09
     digest
    -0.09
    POSITIVE LOGITS
    180
    0.34
    181
    0.19
     adventure
    0.18
    179
    0.17
     aventure
    0.16
     aventura
    0.16
    184
    0.15
    182
    0.15
    178
    0.14
    183
    0.14
    Activations Density 0.079%

    No Known Activations