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. 43891
    Prev
    Next
    INDEX
    Explanations

    preserving files

    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
     calmer
    -0.08
     dozen
    -0.08
    xm
    -0.08
    AU
    -0.07
     calming
    -0.07
     mall
    -0.07
     olema
    -0.07
     야
    -0.07
    ("""↵
    -0.07
     Tro
    -0.07
    POSITIVE LOGITS
     preserved
    0.16
     preserving
    0.15
     intact
    0.15
     preserve
    0.14
     preservation
    0.14
     preserves
    0.14
     Preservation
    0.13
    -pres
    0.13
    original
    0.13
     faithfully
    0.13
    Activations Density 0.013%

    No Known Activations