© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 77905
    Prev
    Next
    INDEX
    Explanations

    decision-making outcomes

    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
     the
    -0.07
    Cand
    -0.07
    Hints
    -0.07
     mor
    -0.07
    pump
    -0.07
    cand
    -0.07
     peptide
    -0.07
    bag
    -0.07
     candidate
    -0.07
    sharp
    -0.06
    POSITIVE LOGITS
     Outcomes
    0.11
     branches
    0.11
     outcomes
    0.10
     Branch
    0.10
     शाख
    0.10
    branches
    0.10
     éxito
    0.09
    _branch
    0.09
     амер
    0.09
    _BRANCH
    0.09
    Activations Density 0.011%

    No Known Activations