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. 11-RESID-POST-AA
    6. 88147
    Prev
    Next
    INDEX
    Explanations

    references

    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
    YYY
    -0.09
     moderated
    -0.09
    Asimismo
    -0.08
    preci
    -0.08
    OSP
    -0.08
    assat
    -0.07
    باش
    -0.07
     tiel
    -0.07
    กล่าว
    -0.07
    621
    -0.07
    POSITIVE LOGITS
     Foundation
    0.08
    Foundation
    0.07
     CF
    0.07
     brit
    0.07
     Linux
    0.07
    /www
    0.07
     Ninja
    0.07
    ­
    0.07
    :**
    0.07
     Kingdom
    0.07
    Activations Density 0.118%

    No Known Activations