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. 58720
    Prev
    Next
    INDEX
    Explanations

    avoiding hazards

    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
    =A
    -0.08
     neurons
    -0.08
    Neuron
    -0.08
    hern
    -0.08
     Someone
    -0.07
     desemp
    -0.07
    _=
    -0.07
    -.
    -0.07
    jac
    -0.07
     someone
    -0.07
    POSITIVE LOGITS
     осторож
    0.12
     prud
    0.11
     meiden
    0.11
     voorzichtig
    0.11
    慎
    0.11
     advised
    0.11
     verstandig
    0.10
     heed
    0.10
     advis
    0.10
     advisable
    0.10
    Activations Density 0.034%

    No Known Activations