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. 103962
    Prev
    Next
    INDEX
    Explanations

    of

    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
     frozen
    -0.08
    Fotos
    -0.08
    Spider
    -0.08
     Fremont
    -0.08
    cemos
    -0.08
     heel
    -0.08
    Frozen
    -0.08
    掲
    -0.07
     soles
    -0.07
     amist
    -0.07
    POSITIVE LOGITS
     hinweg
    0.09
     appar
    0.08
     mitään
    0.08
    Except
    0.08
     оказыва
    0.08
     enthalten
    0.07
     окаж
    0.07
    ensatz
    0.07
    except
    0.07
     vcs
    0.07
    Activations Density 0.013%

    No Known Activations