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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 19306
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     juega
    -0.10
    akukeun
    -0.09
    hawm
    -0.09
    levance
    -0.09
    irg
    -0.09
    caop
    -0.09
    quia
    -0.09
    yuas
    -0.09
    aanse
    -0.09
    că
    -0.09
    POSITIVE LOGITS
     including
    0.08
     maybe
    0.08
     possibly
    0.08
     '?
    0.08
     ?.
    0.08
     unknown
    0.08
     Possibly
    0.08
     Some
    0.07
     ???
    0.07
     সম্ভব
    0.07
    Activations Density 0.018%

    No Known Activations