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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 58796
    Prev
    Next
    INDEX
    Explanations

    Citations and 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
     Wonder
    -0.08
    Wonder
    -0.08
    जे
    -0.08
    Unlock
    -0.08
     оказ
    -0.07
    ifically
    -0.07
     Canc
    -0.07
    _cmp
    -0.07
    जा
    -0.07
    Operate
    -0.07
    POSITIVE LOGITS
    出版
    0.12
     DOI
    0.11
    掲載
    0.10
     publish
    0.09
     publication
    0.09
    publication
    0.09
     keywords
    0.09
     publisher
    0.09
     fehlt
    0.09
    .publisher
    0.09
    Activations Density 0.008%

    No Known Activations