© 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. 97231
    Prev
    Next
    INDEX
    Explanations

    Hungarian

    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
    FFECT
    -0.09
    گذار
    -0.09
    žne
    -0.08
    স্থা
    -0.08
    يرا
    -0.08
    Ζ
    -0.08
    انة
    -0.07
    aceutical
    -0.07
     করছে
    -0.07
    োগ
    -0.07
    POSITIVE LOGITS
    ített
    0.13
    jed
    0.12
    jede
    0.11
    jes
    0.10
    ült
    0.10
    ít
    0.10
    j
    0.08
    eng
    0.08
    尽
    0.08
    jent
    0.08
    Activations Density 0.001%

    No Known Activations