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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48512
    Prev
    Next
    INDEX
    Explanations

    E

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nt
    -0.08
    αιρε
    -0.08
    �
    -0.08
     opposition
    -0.08
     applied
    -0.07
    gmt
    -0.07
     hiss
    -0.07
     invading
    -0.07
    <const
    -0.07
    NT
    -0.07
    POSITIVE LOGITS
    leanor
    0.16
    ileen
    0.15
    vel
    0.14
    llen
    0.14
    ve
    0.13
     Catherine
    0.12
    un
    0.12
    izabeth
    0.12
    una
    0.12
     Emma
    0.12
    Activations Density 0.003%

    No Known Activations