© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1383
    Prev
    Next
    INDEX
    Explanations

    intimacy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ener
    -0.08
     데이터를
    -0.08
     Leb
    -0.07
     пути
    -0.07
     सुर
    -0.07
     ramp
    -0.07
     �
    -0.07
     움직
    -0.07
    _ANAL
    -0.07
    úd
    -0.07
    POSITIVE LOGITS
     worn
    0.08
     penile
    0.08
     workings
    0.07
     ínt
    0.07
     romant
    0.07
    ARRANT
    0.07
    arp
    0.07
    bourne
    0.07
     masse
    0.07
    唐
    0.07
    Activations Density 0.003%

    No Known Activations